<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
tst-pt-gun_gub
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3706
- Bleu: 7.7265
- Gen Len: 63.152
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.7988 | 0.29 | 4000 | 2.5546 | 1.9592 | 58.376 |
| 2.3128 | 0.59 | 8000 | 2.1371 | 4.549 | 71.704 |
| 2.0843 | 0.88 | 12000 | 1.8790 | 5.7485 | 68.216 |
| 1.8776 | 1.18 | 16000 | 1.7351 | 6.2145 | 62.368 |
| 1.7898 | 1.47 | 20000 | 1.6494 | 6.7893 | 63.232 |
| 1.7111 | 1.77 | 24000 | 1.5318 | 7.4069 | 61.24 |
| 1.5854 | 2.06 | 28000 | 1.4736 | 8.2822 | 69.096 |
| 1.5539 | 2.36 | 32000 | 1.4256 | 8.0137 | 62.704 |
| 1.543 | 2.65 | 36000 | 1.3971 | 8.0144 | 62.144 |
| 1.5118 | 2.94 | 40000 | 1.3706 | 7.7265 | 63.152 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
